Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 966 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.4227. Min Act: -0.1700
Data Index: 1623700 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.4540. Min Act: -0.1700
Data Index: 2701192 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.4227. Min Act: -0.1700
Data Index: 6865989 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3913. Min Act: -0.1700
Data Index: 4485275 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3913. Min Act: -0.1700
Data Index: 8047868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 748454 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 7176750 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 2637864 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 7607708 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 6182516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 224905 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 8396498 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3599. Min Act: -0.1700
Data Index: 8432551 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3286. Min Act: -0.1700
Data Index: 3242311 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3286. Min Act: -0.1700
Data Index: 3371717 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3286. Min Act: -0.1700
Data Index: 3716255 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3286. Min Act: -0.1700
Data Index: 3772134 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3286. Min Act: -0.1700
Data Index: 3907017 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3286. Min Act: -0.1700
Data Index: 3914239 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4540. Min Range: -3.4540
Max Act: 3.3286. Min Act: -0.1700
Data Index: 3919987 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19